Zobrazeno 1 - 10
of 60
pro vyhledávání: '"Duarte, Amanda"'
The advances in automatic sign language translation (SLT) to spoken languages have been mostly benchmarked with datasets of limited size and restricted domains. Our work advances the state of the art by providing the first baseline results on How2Sig
Externí odkaz:
http://arxiv.org/abs/2304.06371
Systems that can efficiently search collections of sign language videos have been highlighted as a useful application of sign language technology. However, the problem of searching videos beyond individual keywords has received limited attention in t
Externí odkaz:
http://arxiv.org/abs/2201.02495
Recent work have addressed the generation of human poses represented by 2D/3D coordinates of human joints for sign language. We use the state of the art in Deep Learning for motion transfer and evaluate them on How2Sign, an American Sign Language dat
Externí odkaz:
http://arxiv.org/abs/2012.10941
Autor:
Duarte, Amanda, Palaskar, Shruti, Ventura, Lucas, Ghadiyaram, Deepti, DeHaan, Kenneth, Metze, Florian, Torres, Jordi, Giro-i-Nieto, Xavier
One of the factors that have hindered progress in the areas of sign language recognition, translation, and production is the absence of large annotated datasets. Towards this end, we introduce How2Sign, a multimodal and multiview continuous American
Externí odkaz:
http://arxiv.org/abs/2008.08143
E se nós decidirmos juntos?: uma proposta de criação teatral compartilhada dentro da educação formal
Autor:
Duarte, Amanda
Publikováno v:
Repositório Institucional da UFBAUniversidade Federal da BahiaUFBA.
Submitted by Amanda Duarte (amandasaduarte@gmail.com) on 2018-09-04T15:03:43Z No. of bitstreams: 1 DISSERTAÇÃO PRONTA PARA A ENTREGA.pdf: 2016785 bytes, checksum: 711faaa4e6641ee21a0db1c8fdae94e1 (MD5)
Approved for entry into archive by Ednaid
Approved for entry into archive by Ednaid
Externí odkaz:
http://repositorio.ufba.br/ri/handle/ri/27288
Autor:
Duarte, Amanda, Roldan, Francisco, Tubau, Miquel, Escur, Janna, Pascual, Santiago, Salvador, Amaia, Mohedano, Eva, McGuinness, Kevin, Torres, Jordi, Giro-i-Nieto, Xavier
Speech is a rich biometric signal that contains information about the identity, gender and emotional state of the speaker. In this work, we explore its potential to generate face images of a speaker by conditioning a Generative Adversarial Network (G
Externí odkaz:
http://arxiv.org/abs/1903.10195
The increasing amount of online videos brings several opportunities for training self-supervised neural networks. The creation of large scale datasets of videos such as the YouTube-8M allows us to deal with this large amount of data in manageable way
Externí odkaz:
http://arxiv.org/abs/1801.02200
Publikováno v:
AlephRepositório Institucional da UNESPUniversidade Estadual PaulistaUNESP.
Made available in DSpace on 2014-08-13T14:50:48Z (GMT). No. of bitstreams: 0 Previous issue date: 2013-12-11Bitstream added on 2014-08-13T18:00:29Z : No. of bitstreams: 1 000758886.pdf: 1623359 bytes, checksum: 421c293d525c9437f7bb8843242c9b4e (MD5)<
Externí odkaz:
http://hdl.handle.net/11449/108626
Autor:
Gaya, Joel D. O., Codevilla, Felipe, Duarte, Amanda C., Drews-Jr, Paulo L., Botelho, Silvia S.
This paper describes a method to restore degraded images captured in a participating media -- fog, turbid water, sand storm, etc. Differently from the related work that only deal with a medium, we obtain generality by using an image formation model a
Externí odkaz:
http://arxiv.org/abs/1603.01864